WO2016132149A1 - Accélération de processus d'optimisation de machines - Google Patents
Accélération de processus d'optimisation de machines Download PDFInfo
- Publication number
- WO2016132149A1 WO2016132149A1 PCT/GB2016/050427 GB2016050427W WO2016132149A1 WO 2016132149 A1 WO2016132149 A1 WO 2016132149A1 GB 2016050427 W GB2016050427 W GB 2016050427W WO 2016132149 A1 WO2016132149 A1 WO 2016132149A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- visual data
- video
- quality
- resolution
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 450
- 230000008569 process Effects 0.000 title description 145
- 238000012549 training Methods 0.000 claims abstract description 117
- 230000000007 visual effect Effects 0.000 claims description 698
- 238000013459 approach Methods 0.000 claims description 101
- 238000013527 convolutional neural network Methods 0.000 claims description 62
- 238000010801 machine learning Methods 0.000 claims description 56
- 230000006870 function Effects 0.000 claims description 42
- 230000002708 enhancing effect Effects 0.000 claims description 28
- 238000013507 mapping Methods 0.000 claims description 16
- 230000000306 recurrent effect Effects 0.000 claims description 10
- 238000011524 similarity measure Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 239000010410 layer Substances 0.000 description 83
- 230000005540 biological transmission Effects 0.000 description 80
- 238000007906 compression Methods 0.000 description 57
- 230000006835 compression Effects 0.000 description 56
- 238000013528 artificial neural network Methods 0.000 description 41
- 238000012986 modification Methods 0.000 description 32
- 230000004048 modification Effects 0.000 description 32
- 238000012545 processing Methods 0.000 description 30
- 125000004429 atom Chemical group 0.000 description 28
- 230000001965 increasing effect Effects 0.000 description 23
- 238000004458 analytical method Methods 0.000 description 19
- 238000005070 sampling Methods 0.000 description 13
- 230000001360 synchronised effect Effects 0.000 description 12
- 238000013135 deep learning Methods 0.000 description 11
- 238000000605 extraction Methods 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 11
- 230000009467 reduction Effects 0.000 description 11
- 230000003139 buffering effect Effects 0.000 description 8
- 230000001419 dependent effect Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 8
- 230000018109 developmental process Effects 0.000 description 8
- 230000033001 locomotion Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 7
- 230000007704 transition Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000002123 temporal effect Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000012935 Averaging Methods 0.000 description 4
- 241000854350 Enicospilus group Species 0.000 description 4
- 238000012952 Resampling Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000009499 grossing Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000003064 k means clustering Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 3
- 230000001934 delay Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000007670 refining Methods 0.000 description 3
- 238000013341 scale-up Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006837 decompression Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000005284 basis set Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 201000011243 gastrointestinal stromal tumor Diseases 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000012010 growth Effects 0.000 description 1
- 125000005843 halogen group Chemical group 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000010380 label transfer Methods 0.000 description 1
- 239000002346 layers by function Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/60—Image enhancement or restoration using machine learning, e.g. neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/117—Filters, e.g. for pre-processing or post-processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/142—Detection of scene cut or scene change
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/154—Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/176—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/177—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a group of pictures [GOP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/179—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a scene or a shot
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/30—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability
- H04N19/31—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability in the temporal domain
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/30—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability
- H04N19/33—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability in the spatial domain
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/30—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability
- H04N19/36—Scalability techniques involving formatting the layers as a function of picture distortion after decoding, e.g. signal-to-noise [SNR] scalability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/46—Embedding additional information in the video signal during the compression process
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/46—Embedding additional information in the video signal during the compression process
- H04N19/463—Embedding additional information in the video signal during the compression process by compressing encoding parameters before transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
- H04N19/59—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/80—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/86—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving reduction of coding artifacts, e.g. of blockiness
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
- H04N7/0117—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level involving conversion of the spatial resolution of the incoming video signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
- H04N19/63—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/87—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving scene cut or scene change detection in combination with video compression
Definitions
- the system then separates a first section of the video data 1410 into single frames at step 1420, i.e. into a sequence of images at the full SD resolution of the video data 1410. For some video codecs, this will involve "uncompressing” or restoring the video data as, for example, common video compression techniques remove redundant (non-changing) features from sequential frames.
- An upscaling technique 1430 is then used on one or more of the frames or sections of frames, to increase the resolution of the areas upon which it is used.
- the higher resolution frames are then optionally processed at step 1440 into a format suitable for output as a video.
- the video being composed of higher resolution frames, will be in the form of a higher resolution video 1450 than the original video file.
- Super resolution techniques fall predominantly into one of two main fields; optical super resolution techniques and geometrical super resolution techniques.
- Optical super resolution techniques allow an image to exceed the diffraction limit originally placed on it, while geometrical super resolution techniques increase the resolution from digital imaging sensors.
- geometrical super resolution seems to be the predominant technique.
- FIG. 1 An example of an over-complete dictionary is shown in Figure 1 , where a 16 x 16 pixel patch is represented by a linear combination of 16 x 16 dictionary atoms 5 that is drawn from the collection of atoms that is the dictionary 1. It is noted that the atoms are not selected locally within the dictionary, but instead are chosen as the linear combination that best approximates the signal patch for a maximum number of atoms allowed and irrespective of their location within the dictionary. Without a constraint that the atoms must be orthogonal to one another, larger dictionaries than the signal space that the dictionary is intended to represent are created.
- the transform domain can be a dictionary of image atoms, which can be learnt through a training process known as dictionary learning that tries to discover the correspondence between low-resolution and high-resolution sections of images (or "patches").
- Dictionary learning uses a set of linear representations to represent an image and, where an over-complete dictionary is used, a plurality of linear representations can be used to represent each image patch to increase the accuracy of the representation.
- a stored library of learned hierarchical algorithms allows selection of a hierarchical algorithm for comparison without having to develop them or obtain them from an external source.
- the comparison can be between a plurality of algorithms in the library.
- Use of such a library may result in the faster selection of a suitable hierarchical algorithm for enhancing the visual data or, in some embodiments, the most suitable hierarchical algorithm in a library (for example, by basing a measure of suitability on a predetermined metric).
- metric data can be used to determine whether the trained model would be suitable for use with visual data having similar metric data
- metric data can be used to compare to metric data associated with further visual data to select a suitable hierarchical algorithm to enhance that further visual data.
- a specific hierarchical algorithm need not be trained for every set of visual data; existing trained hierarchical algorithms can instead be used to enhance similar sets of visual data to that on which they were trained.
- the lower quality version together with a reference to the model to be used for reconstruction can still allow for less data to be transmitted than if the original higher-quality version of the same section of visual data is transmitted.
- developing multiple hierarchical algorithms in parallel while encoding the visual data can speed up the process of preparing the visual data and hierarchical algorithm for communication across a network.
- developing multiple hierarchical algorithms in parallel a greater number of possible algorithm structures can be explored and the most suitable chosen.
- transmitting the whole of the developed hierarchical algorithm to the second node ensures that the developed hierarchical algorithm is available for use at the second node.
- a method further comprising the step of: receiving a higher- quality section of visual data from a third node, before transmitting the higher- quality section of visual data to the first node.
- each frame can down-sampled into lower-resolution frames at a suitably low resolution.
- this step can occur before the frames are grouped into scenes in step 150.
- the lower- resolution frame is optionally 33% to 50% of the data size relative to the data size of the original-resolution frame, but can be any resolution that is lower than the original resolution of the video.
- the quality can be reduced by quantisation and/or compression instead of reducing the resolution of the visual data or in addition to reducing the resolution of the visual data.
- Embodiments can use dictionary learning reconstruction models or convolutional neural network reconstruction models for up-scaling, or a mixture of these two techniques.
- a library of reconstruction models is stored that can be generated from example, or training, video data where both the original and reduced- resolution video can be compared.
- data needs to be stored relating to the example or training video for each reconstruction model in the library to enable each model to be matched to a scene that is being up-scaled.
- the data stored relating to the example or training video can be metadata or metrics related to the video data, or it can be samples or features of the example or training video.
- Original video data 1010 is provided into the method or system using the technique and is a high-resolution video, for example having a resolution of 1920 pixels by 1080 pixels (also known as "1080p” video) or 3840 pixels by 2160 pixels (also known as "4K” video).
- This video data can be encoded in a variety of known video codecs, such as H.264 or VP9 but can be any video data for which the system or method is able to decode into the component frames of the video.
- this step can occur before the frames are grouped into scenes.
- the lower- resolution frame is preferably 33% to 50% of the data size relative to the data size of the original-resolution frame, while the representations of the frame can be anything from 1 % to 50% of the data size of the original-resolution frame.
- the lower resolution frame can have any resolution that is lower than the original resolution of the video.
- Figure 13 shows a further method of decoding the received information at the second node to reproduce substantially the higher resolution video.
- the package transmitted at step 1260 of Figure 12 is received by the second node at step 1310, and unpacked at step 1320.
- the references to known models are used to locate the known reconstruction models stored in a library at the second node at step 1330.
- the modifications corresponding to these known reconstruction models are then applied at step 1340 to reproduce the optimised reconstruction model generated by the machine learning process in step 1260 of Figure 12.
- This model is optimised to substantially reproduce the original higher resolution video 1260 without the need for it to be applied to a corresponding low resolution video sample.
- the second node can substantially reconstruct the original high resolution video from only the modified reconstruction model.
- This reconstruction is performed at step 1350, and the resulting reconstructed higher resolution video is output at step 1360.
- fully connected neural networks can't scale up to larger sizes of network easily as the computational complexity soon becomes too great as the size of the network scales, but this depends on the application of the neural network and also other factors such as the kernel and filter sizes.
- Figure 22 illustrates an overview of embodiments of a method of generating models for use in image artefact removal. These embodiments can be used in combination with other embodiments, and alternative and optional portions of embodiments, described elsewhere in this specification.
- the original training scene generated in the scene selection process is used to generate multiple models for the same scene content type by repeating the compression and quantisation process with different levels of compression and/or quantisation, or by using different compression and/or quantisation algorithms.
- this approach introduces a different level of artefact severity to the scene.
- the training and optimisation process can then be repeated to generate a new image artefact removal model for the same content, but a different level of artefact severity.
- the received video/image data can already have been divided into scenes and classified by the transmitting network node, in which case the data received by the receiving node will contain metadata for each of the scenes contained within it that identifies the scene content type.
- the hierarchical algorithms can be trained using training data corresponding to the exact visual data that will be transmitted across the network. In such embodiments, this approach can be particularly useful in situations where the visual data is known in advance, and where the visual data is likely to be transmitted across the network multiple times.
- the hierarchical models can be trained on sections of an episode of a TV program that will be made available on an on-demand streaming service. In such embodiments the models trained on that particular episode can be transmitted alongside the lower-quality visual data and be used to enhance the lower-quality visual data to a higher-quality version of that episode.
- 'frame' particularly in reference to grouping multiple frames into scenes, can refer to both an entire frame of a video and an area comprising a smaller section of a frame.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Image Analysis (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
- Image Processing (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Databases & Information Systems (AREA)
- Picture Signal Circuits (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
L'invention concerne un procédé d'entraînement d'algorithmes hiérarchiques ayant fait l'objet d'un apprentissage, le procédé comportant les étapes consistant à recevoir des données d'entrée et à générer des métriques à partir des données d'entrée. Au moins un algorithme hiérarchique est ensuite sélectionné parmi une pluralité d'algorithmes hiérarchiques prédéterminés sur la base d'une comparaison des métriques générées à partir des données d'entrée et de métriques similaires pour chaque algorithme de la pluralité d'algorithmes hiérarchiques prédéterminés. L'algorithme hiérarchique sélectionné est développé d'après les données d'entrée et l'algorithme hiérarchique développé est délivré.
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP16706419.5A EP3259918B1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de la résolution à l'aide d'une pluralité de réseaux de neurones |
EP16715067.1A EP3278559B1 (fr) | 2015-03-31 | 2016-03-31 | Apprentissage de processus vidéo bout-à-bout |
PCT/GB2016/050922 WO2016156864A1 (fr) | 2015-03-31 | 2016-03-31 | Apprentissage de processus vidéo bout-à-bout |
US15/680,708 US10516890B2 (en) | 2015-02-19 | 2017-08-18 | Accelerating machine optimisation processes |
US15/707,294 US10666962B2 (en) | 2015-03-31 | 2017-09-18 | Training end-to-end video processes |
Applications Claiming Priority (16)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB1502753.5 | 2015-02-19 | ||
GB201502753A GB201502753D0 (en) | 2015-02-19 | 2015-02-19 | Method for encoding and decoding video data |
GB201503427A GB201503427D0 (en) | 2015-02-27 | 2015-02-27 | Method for adaptive upscaling of video data |
GB1503427.5 | 2015-02-27 | ||
GB1505544.5 | 2015-03-31 | ||
GBGB1505544.5A GB201505544D0 (en) | 2015-03-31 | 2015-03-31 | Method for accelerating machine optimisation processes or algorithms |
GBGB1507141.8A GB201507141D0 (en) | 2015-04-27 | 2015-04-27 | Method for encoding and decoding video data using reconstruction libraries |
GB1507141.8 | 2015-04-27 | ||
GB1508742.2 | 2015-05-21 | ||
GBGB1508742.2A GB201508742D0 (en) | 2015-05-21 | 2015-05-21 | A method for encoding and decoding video data |
GBGB1511231.1A GB201511231D0 (en) | 2015-06-25 | 2015-06-25 | Method for real-time encoding and decoding of video data |
GB1511231.1 | 2015-06-25 | ||
GB1519425.1 | 2015-11-03 | ||
GBGB1519425.1A GB201519425D0 (en) | 2015-11-03 | 2015-11-03 | Image fidelity correction and restoration |
GBGB1519687.6A GB201519687D0 (en) | 2015-02-19 | 2015-11-06 | Method for encoding and decoding video data |
GB1519687.6 | 2015-11-06 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/680,708 Continuation US10516890B2 (en) | 2015-02-19 | 2017-08-18 | Accelerating machine optimisation processes |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016132149A1 true WO2016132149A1 (fr) | 2016-08-25 |
Family
ID=56688725
Family Applications (10)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/GB2016/050424 WO2016132146A1 (fr) | 2015-02-19 | 2016-02-19 | Traitement visuel à l'aide de convolutions de sous-pixels |
PCT/GB2016/050429 WO2016132151A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles à l'aide de convolutions progressives |
PCT/GB2016/050427 WO2016132149A1 (fr) | 2015-02-19 | 2016-02-19 | Accélération de processus d'optimisation de machines |
PCT/GB2016/050426 WO2016132148A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage machine pour un traitement visuel |
PCT/GB2016/050425 WO2016132147A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles |
PCT/GB2016/050423 WO2016132145A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage en ligne d'algorithmes hiérarchiques |
PCT/GB2016/050432 WO2016132154A1 (fr) | 2015-02-19 | 2016-02-19 | Traitement visuel à l'aide d'une interpolation temporelle et spatiale |
PCT/GB2016/050430 WO2016132152A1 (fr) | 2015-02-19 | 2016-02-19 | Interpolation de données visuelles |
PCT/GB2016/050428 WO2016132150A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles en utilisant et augmentant des bibliothèques de modèles |
PCT/GB2016/050431 WO2016132153A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage hors ligne d'algorithmes hiérarchiques |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/GB2016/050424 WO2016132146A1 (fr) | 2015-02-19 | 2016-02-19 | Traitement visuel à l'aide de convolutions de sous-pixels |
PCT/GB2016/050429 WO2016132151A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles à l'aide de convolutions progressives |
Family Applications After (7)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/GB2016/050426 WO2016132148A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage machine pour un traitement visuel |
PCT/GB2016/050425 WO2016132147A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles |
PCT/GB2016/050423 WO2016132145A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage en ligne d'algorithmes hiérarchiques |
PCT/GB2016/050432 WO2016132154A1 (fr) | 2015-02-19 | 2016-02-19 | Traitement visuel à l'aide d'une interpolation temporelle et spatiale |
PCT/GB2016/050430 WO2016132152A1 (fr) | 2015-02-19 | 2016-02-19 | Interpolation de données visuelles |
PCT/GB2016/050428 WO2016132150A1 (fr) | 2015-02-19 | 2016-02-19 | Amélioration de données visuelles en utilisant et augmentant des bibliothèques de modèles |
PCT/GB2016/050431 WO2016132153A1 (fr) | 2015-02-19 | 2016-02-19 | Apprentissage hors ligne d'algorithmes hiérarchiques |
Country Status (6)
Country | Link |
---|---|
US (10) | US10523955B2 (fr) |
EP (11) | EP3259920A1 (fr) |
DE (6) | DE202016009102U1 (fr) |
ES (2) | ES2873845T3 (fr) |
GB (5) | GB2539845B (fr) |
WO (10) | WO2016132146A1 (fr) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018125580A1 (fr) * | 2016-12-30 | 2018-07-05 | Konica Minolta Laboratory U.S.A., Inc. | Segmentation de glande à réseaux de déconvolution multi-niveaux supervisés en profondeur |
CN110378854A (zh) * | 2019-07-17 | 2019-10-25 | 上海商汤智能科技有限公司 | 机器人图像增强方法及装置 |
Families Citing this family (281)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9532080B2 (en) | 2012-05-31 | 2016-12-27 | Sonic Ip, Inc. | Systems and methods for the reuse of encoding information in encoding alternative streams of video data |
US9357210B2 (en) | 2013-02-28 | 2016-05-31 | Sonic Ip, Inc. | Systems and methods of encoding multiple video streams for adaptive bitrate streaming |
EP3259920A1 (fr) | 2015-02-19 | 2017-12-27 | Magic Pony Technology Limited | Traitement visuel à l'aide d'une interpolation temporelle et spatiale |
RU2596062C1 (ru) | 2015-03-20 | 2016-08-27 | Автономная Некоммерческая Образовательная Организация Высшего Профессионального Образования "Сколковский Институт Науки И Технологий" | Способ коррекции изображения глаз с использованием машинного обучения и способ машинного обучения |
GB201604672D0 (en) | 2016-03-18 | 2016-05-04 | Magic Pony Technology Ltd | Generative methods of super resolution |
GB201603144D0 (en) | 2016-02-23 | 2016-04-06 | Magic Pony Technology Ltd | Training end-to-end video processes |
GB201604345D0 (en) | 2016-03-14 | 2016-04-27 | Magic Pony Technology Ltd | Super resolution using fidelity transfer |
WO2016156864A1 (fr) | 2015-03-31 | 2016-10-06 | Magic Pony Technology Limited | Apprentissage de processus vidéo bout-à-bout |
EP3400706B1 (fr) | 2016-01-05 | 2022-04-13 | RealD Spark, LLC | Correction du regard d'images multi-vues |
US10373019B2 (en) * | 2016-01-13 | 2019-08-06 | Ford Global Technologies, Llc | Low- and high-fidelity classifiers applied to road-scene images |
US10402700B2 (en) * | 2016-01-25 | 2019-09-03 | Deepmind Technologies Limited | Generating images using neural networks |
EP3395073A4 (fr) * | 2016-02-04 | 2019-04-10 | Mediatek Inc. | Procédé et appareil de codage vidéo au moyen de filtres de boucle adaptatifs non locaux |
EP3427195B1 (fr) * | 2016-03-11 | 2024-05-01 | Telecom Italia S.p.A. | Réseaux neuronaux convolutifs, en particulier pour analyse d'images |
US10387743B2 (en) * | 2016-03-16 | 2019-08-20 | Ramot At Tel-Aviv University Ltd. | Reconstruction of high-quality images from a binary sensor array |
US10089717B2 (en) * | 2016-04-05 | 2018-10-02 | Flipboard, Inc. | Image scaling using a convolutional neural network |
EP3298579B1 (fr) | 2016-04-12 | 2021-07-21 | Magic Pony Technology Limited | Traitement de données visuelles à l'aide des réseaux d'énergie |
ES2853700T3 (es) | 2016-04-15 | 2021-09-17 | Magic Pony Tech Limited | Compensación de movimiento utilizando interpolación de imagen temporal |
GB201608259D0 (en) | 2016-05-11 | 2016-06-22 | Magic Pony Technology Ltd | Feature transfer |
US10319076B2 (en) * | 2016-06-16 | 2019-06-11 | Facebook, Inc. | Producing higher-quality samples of natural images |
CN106447609A (zh) * | 2016-08-30 | 2017-02-22 | 上海交通大学 | 一种基于深度卷积神经网络的图像超分辨方法 |
CN106355579A (zh) * | 2016-09-14 | 2017-01-25 | 南京理工大学 | 烟条表面褶皱的缺陷检测方法 |
WO2018051336A1 (fr) * | 2016-09-18 | 2018-03-22 | Yeda Research And Development Co. Ltd. | Systèmes et procédés de génération d'images 3d sur la base d'un éclairage fluorescent |
CN109952581A (zh) | 2016-09-28 | 2019-06-28 | D5A1有限责任公司 | 用于机器学习系统的学习教练 |
KR102384234B1 (ko) * | 2016-10-26 | 2022-04-07 | 삼성전자주식회사 | 영상처리장치, 영상처리방법 및 컴퓨터 판독가능 기록 매체 |
US10289951B2 (en) * | 2016-11-02 | 2019-05-14 | Adobe Inc. | Video deblurring using neural networks |
US10573040B2 (en) * | 2016-11-08 | 2020-02-25 | Adobe Inc. | Image modification using detected symmetry |
US10192295B2 (en) * | 2016-11-09 | 2019-01-29 | AI Analysis, Inc. | Methods and systems for normalizing images |
US10701394B1 (en) | 2016-11-10 | 2020-06-30 | Twitter, Inc. | Real-time video super-resolution with spatio-temporal networks and motion compensation |
CN108133222B (zh) | 2016-12-01 | 2021-11-02 | 富士通株式会社 | 为数据库确定卷积神经网络cnn模型的装置和方法 |
US11593632B2 (en) * | 2016-12-15 | 2023-02-28 | WaveOne Inc. | Deep learning based on image encoding and decoding |
CN106791927A (zh) * | 2016-12-23 | 2017-05-31 | 福建帝视信息科技有限公司 | 一种基于深度学习的视频增强与传输方法 |
CN106686385B (zh) | 2016-12-30 | 2018-09-25 | 平安科技(深圳)有限公司 | 视频压缩感知重构方法及装置 |
CN106910161B (zh) * | 2017-01-24 | 2020-06-19 | 华南理工大学 | 一种基于深度卷积神经网络的单幅图像超分辨率重建方法 |
JP7065266B2 (ja) * | 2017-02-03 | 2022-05-12 | パナソニックIpマネジメント株式会社 | 学習済みモデル提供方法および学習済みモデル提供装置 |
WO2018170393A2 (fr) * | 2017-03-17 | 2018-09-20 | Portland State University | Interpolation d'images par convolution adaptative et convolution séparable adaptative |
US10276134B2 (en) * | 2017-03-22 | 2019-04-30 | International Business Machines Corporation | Decision-based data compression by means of deep learning technologies |
US11915152B2 (en) | 2017-03-24 | 2024-02-27 | D5Ai Llc | Learning coach for machine learning system |
CN108664981B (zh) * | 2017-03-30 | 2021-10-26 | 北京航空航天大学 | 显著图像提取方法及装置 |
US10838922B2 (en) * | 2017-03-31 | 2020-11-17 | International Business Machines Corporation | Data compression by using cognitive created dictionaries |
US10482609B2 (en) | 2017-04-04 | 2019-11-19 | General Electric Company | Optical flow determination system |
US10410322B2 (en) | 2017-04-05 | 2019-09-10 | Here Global B.V. | Deep convolutional image up-sampling |
US11037330B2 (en) | 2017-04-08 | 2021-06-15 | Intel Corporation | Low rank matrix compression |
US10489887B2 (en) * | 2017-04-10 | 2019-11-26 | Samsung Electronics Co., Ltd. | System and method for deep learning image super resolution |
US10552977B1 (en) | 2017-04-18 | 2020-02-04 | Twitter, Inc. | Fast face-morphing using neural networks |
US11164071B2 (en) * | 2017-04-18 | 2021-11-02 | Samsung Electronics Co., Ltd. | Method and apparatus for reducing computational complexity of convolutional neural networks |
US10922556B2 (en) * | 2017-04-28 | 2021-02-16 | Intel Corporation | Storage system of DNN outputs for black box |
CN107103585B (zh) * | 2017-04-28 | 2020-09-11 | 广东工业大学 | 一种图像超分辨率系统 |
GB201707912D0 (en) * | 2017-05-17 | 2017-06-28 | Microsoft Technology Licensing Llc | Data compression system |
WO2018212599A1 (fr) * | 2017-05-17 | 2018-11-22 | Samsung Electronics Co., Ltd. | Procédé de traitement super-résolution pour image animée et appareil de traitement d'image associé |
KR102511059B1 (ko) * | 2017-05-17 | 2023-03-17 | 삼성전자주식회사 | 동영상의 초해상 처리 방법 및 이를 위한 영상 처리 장치 |
CN108959312B (zh) * | 2017-05-23 | 2021-01-29 | 华为技术有限公司 | 一种多文档摘要生成的方法、装置和终端 |
KR20210119578A (ko) * | 2017-05-26 | 2021-10-05 | 에이에스엠엘 네델란즈 비.브이. | 기계 학습에 기초한 어시스트 피처 배치 |
CN110892417B (zh) | 2017-06-05 | 2024-02-20 | D5Ai有限责任公司 | 具有学习教练的异步代理以及在不降低性能的情况下在结构上修改深度神经网络 |
CN109218727B (zh) * | 2017-06-30 | 2021-06-25 | 书法报视频媒体(湖北)有限公司 | 视频处理的方法和装置 |
US10776982B2 (en) | 2017-07-03 | 2020-09-15 | Artomatix Ltd. | Systems and methods for providing non-parametric texture synthesis of arbitrary shape and/or material data in a unified framework |
US11190784B2 (en) | 2017-07-06 | 2021-11-30 | Samsung Electronics Co., Ltd. | Method for encoding/decoding image and device therefor |
US10986356B2 (en) | 2017-07-06 | 2021-04-20 | Samsung Electronics Co., Ltd. | Method for encoding/decoding image and device therefor |
WO2019009449A1 (fr) * | 2017-07-06 | 2019-01-10 | 삼성전자 주식회사 | Procédé et dispositif de codage/décodage d'image |
US11308361B1 (en) | 2017-07-07 | 2022-04-19 | Twitter, Inc. | Checkerboard artifact free sub-pixel convolution |
US11861811B2 (en) | 2017-07-27 | 2024-01-02 | Nvidia Corporation | Neural network system with temporal feedback for denoising of rendered sequences |
US11475542B2 (en) | 2017-07-27 | 2022-10-18 | Nvidia Corporation | Neural network system with temporal feedback for adaptive sampling and denoising of rendered sequences |
US11557022B2 (en) | 2017-07-27 | 2023-01-17 | Nvidia Corporation | Neural network system with temporal feedback for denoising of rendered sequences |
US10740985B2 (en) | 2017-08-08 | 2020-08-11 | Reald Spark, Llc | Adjusting a digital representation of a head region |
EP3447721A1 (fr) * | 2017-08-24 | 2019-02-27 | Agfa Nv | Procédé de génération d'une image tomographique améliorée d'un objet |
US20200242730A1 (en) * | 2017-09-04 | 2020-07-30 | Semiconductor Energy Laboratory Co., Ltd. | Image processing method, semiconductor device, and electronic device |
US11170467B2 (en) * | 2017-09-05 | 2021-11-09 | Dish Network L.L.C. | Systems and methods for graphics adjustment based on output resolution |
US10713535B2 (en) * | 2017-09-15 | 2020-07-14 | NovuMind Limited | Methods and processes of encrypted deep learning services |
US10891715B2 (en) * | 2017-09-22 | 2021-01-12 | Continental Automotive Systems, Inc. | Deep neural network for image enhancement |
US10482575B2 (en) * | 2017-09-28 | 2019-11-19 | Intel Corporation | Super-resolution apparatus and method for virtual and mixed reality |
US10043113B1 (en) * | 2017-10-04 | 2018-08-07 | StradVision, Inc. | Method and device for generating feature maps by using feature upsampling networks |
US9984325B1 (en) * | 2017-10-04 | 2018-05-29 | StradVision, Inc. | Learning method and learning device for improving performance of CNN by using feature upsampling networks, and testing method and testing device using the same |
US11122238B1 (en) * | 2017-11-07 | 2021-09-14 | Twitter, Inc. | Frame interpolation with multi-scale deep loss functions and generative adversarial networks |
EP3714404A4 (fr) * | 2017-11-26 | 2021-08-18 | Yeda Research and Development Co. Ltd | Rehaussement et manipulation de signal à l'aide d'un réseau profond spécifique d'un signal |
CN108012157B (zh) * | 2017-11-27 | 2020-02-04 | 上海交通大学 | 用于视频编码分数像素插值的卷积神经网络的构建方法 |
CN108108738B (zh) * | 2017-11-28 | 2018-11-16 | 北京达佳互联信息技术有限公司 | 图像处理方法、装置及终端 |
WO2019104705A1 (fr) * | 2017-12-01 | 2019-06-06 | 华为技术有限公司 | Procédé et dispositif de traitement d'image |
US10460259B2 (en) | 2017-12-04 | 2019-10-29 | Bank Of America Corporation | Dynamic progress recognition and recommendations based on machine learning |
US10540574B2 (en) * | 2017-12-07 | 2020-01-21 | Shanghai Cambricon Information Technology Co., Ltd | Image compression method and related device |
US10722210B2 (en) * | 2017-12-14 | 2020-07-28 | Siemens Healthcare Gmbh | Method for memorable image generation for anonymized three-dimensional medical image workflows |
US10579908B2 (en) * | 2017-12-15 | 2020-03-03 | Google Llc | Machine-learning based technique for fast image enhancement |
US11074671B2 (en) * | 2017-12-18 | 2021-07-27 | Samsung Electronics Co., Ltd. | Electronic apparatus and control method thereof |
EP3506633A1 (fr) * | 2017-12-19 | 2019-07-03 | Axis AB | Procédé et système de codage vidéo |
CN109961396B (zh) * | 2017-12-25 | 2020-12-22 | 中国科学院沈阳自动化研究所 | 一种基于卷积神经网络的图像超分辨率重建方法 |
KR102314703B1 (ko) * | 2017-12-26 | 2021-10-18 | 에스케이하이닉스 주식회사 | 이미지 처리를 위한 조인트 딕셔너리 생성 방법, 그 조인트 딕셔너리들을 이용한 인터레이스 기반 하이 다이나믹 레인지 이미징 장치 및 그 이미지 처리 방법 |
CN108062780B (zh) * | 2017-12-29 | 2019-08-09 | 百度在线网络技术(北京)有限公司 | 图像压缩方法和装置 |
KR102050780B1 (ko) * | 2018-01-10 | 2019-12-02 | 한국과학기술원 | 신경망을 이용한 컨텐츠 인지 기반 컨텐츠 전송 서버 장치 및 방법 |
CN108184128A (zh) * | 2018-01-11 | 2018-06-19 | 安徽优思天成智能科技有限公司 | 基于深度神经网络的视频序列丢失帧预测恢复方法 |
CN108322685B (zh) * | 2018-01-12 | 2020-09-25 | 广州华多网络科技有限公司 | 视频插帧方法、存储介质以及终端 |
CN108259994B (zh) * | 2018-01-15 | 2020-10-30 | 复旦大学 | 一种提高视频空间分辨率的方法 |
US20190228313A1 (en) * | 2018-01-23 | 2019-07-25 | Insurance Services Office, Inc. | Computer Vision Systems and Methods for Unsupervised Representation Learning by Sorting Sequences |
US11289125B1 (en) * | 2018-01-25 | 2022-03-29 | Disney Enterprises, Inc. | Digital conformation of media content |
CN110087084B (zh) * | 2018-01-25 | 2022-03-18 | 联咏科技股份有限公司 | 视频处理装置及视频处理方法 |
US11321612B2 (en) | 2018-01-30 | 2022-05-03 | D5Ai Llc | Self-organizing partially ordered networks and soft-tying learned parameters, such as connection weights |
CN108495132B (zh) * | 2018-02-05 | 2019-10-11 | 西安电子科技大学 | 基于轻量级深度卷积网络的遥感影像大倍率压缩方法 |
KR102237288B1 (ko) * | 2018-02-07 | 2021-04-07 | 울산과학기술원 | 기계학습 알고리즘을 이용한 이미지 변환 방법 및 장치 |
US11017575B2 (en) | 2018-02-26 | 2021-05-25 | Reald Spark, Llc | Method and system for generating data to provide an animated visual representation |
CN108416748A (zh) * | 2018-02-26 | 2018-08-17 | 阿博茨德(北京)科技有限公司 | Jpeg压缩文档的图像预处理方法及装置 |
US11392802B2 (en) | 2018-03-07 | 2022-07-19 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US11265168B2 (en) | 2018-03-07 | 2022-03-01 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US11502841B2 (en) | 2018-03-07 | 2022-11-15 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US11210375B2 (en) | 2018-03-07 | 2021-12-28 | Private Identity Llc | Systems and methods for biometric processing with liveness |
US11394552B2 (en) | 2018-03-07 | 2022-07-19 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US11789699B2 (en) | 2018-03-07 | 2023-10-17 | Private Identity Llc | Systems and methods for private authentication with helper networks |
US10721070B2 (en) * | 2018-03-07 | 2020-07-21 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US11170084B2 (en) | 2018-06-28 | 2021-11-09 | Private Identity Llc | Biometric authentication |
US11489866B2 (en) | 2018-03-07 | 2022-11-01 | Private Identity Llc | Systems and methods for private authentication with helper networks |
US11138333B2 (en) | 2018-03-07 | 2021-10-05 | Private Identity Llc | Systems and methods for privacy-enabled biometric processing |
US10938852B1 (en) | 2020-08-14 | 2021-03-02 | Private Identity Llc | Systems and methods for private authentication with helper networks |
CN108346133B (zh) * | 2018-03-15 | 2021-06-04 | 武汉大学 | 一种面向视频卫星超分辨率重建的深度学习网络训练方法 |
CN110324635B (zh) * | 2018-03-30 | 2021-06-15 | 北京大学 | 分像素插值方法、系统、计算机设备和介质 |
CN110324620B (zh) * | 2018-03-30 | 2021-08-24 | 杭州海康威视数字技术股份有限公司 | 帧内预测方法、装置、电子设备及机器可读存储介质 |
US11657264B2 (en) * | 2018-04-09 | 2023-05-23 | Nokia Technologies Oy | Content-specific neural network distribution |
WO2019197712A1 (fr) * | 2018-04-09 | 2019-10-17 | Nokia Technologies Oy | Appareil, procédé, et programme informatique destiné au codage et au décodage vidéo |
US11108843B2 (en) * | 2018-04-09 | 2021-08-31 | Lumenradio Ab | Streaming using constrained dynamic multi-hop network |
WO2019197715A1 (fr) * | 2018-04-09 | 2019-10-17 | Nokia Technologies Oy | Appareil, procédé et programme informatique pour le fonctionnement d'un réseau neuronal |
KR102082816B1 (ko) * | 2018-04-24 | 2020-02-28 | 주식회사 지디에프랩 | 스트리밍 파일의 해상도 개선 방법 |
WO2019209007A1 (fr) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | Système de compression et de décompression d'image fondé sur l'ai |
WO2019209006A1 (fr) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | Procédé d'amélioration de la résolution de fichiers de diffusion en flux |
WO2019209008A1 (fr) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | Système pour améliorer une qualité vidéo au moyen d'une technique d'extraction de macrobloc modifiée |
WO2019209005A1 (fr) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | Système d'amélioration de résolution fondé sur l'intelligence artificielle |
CN108596855A (zh) * | 2018-04-28 | 2018-09-28 | 国信优易数据有限公司 | 一种视频图像质量增强方法、装置以及视频画质增强方法 |
CN110458754B (zh) * | 2018-05-07 | 2021-12-03 | Tcl科技集团股份有限公司 | 图像生成方法及终端设备 |
CN108765287B (zh) * | 2018-05-09 | 2022-02-11 | 浙江师范大学 | 一种基于非局部均值的图像超分辨率方法 |
US11423312B2 (en) | 2018-05-14 | 2022-08-23 | Samsung Electronics Co., Ltd | Method and apparatus for universal pruning and compression of deep convolutional neural networks under joint sparsity constraints |
JP7014044B2 (ja) * | 2018-05-15 | 2022-02-01 | コニカミノルタ株式会社 | 超音波診断装置 |
US11423867B2 (en) * | 2018-05-29 | 2022-08-23 | Lg Electronics Inc. | Signal processing device and image display apparatus including the same |
US11941501B2 (en) * | 2018-05-30 | 2024-03-26 | Samsung Electronics Co., Ltd. | Electronic apparatus and control method thereof |
WO2019236251A1 (fr) * | 2018-06-04 | 2019-12-12 | Lightmatter, Inc. | Couches convolutionnelles pour réseaux neuronaux utilisant une nanophotonique programmable |
US10885608B2 (en) * | 2018-06-06 | 2021-01-05 | Adobe Inc. | Super-resolution with reference images |
JP7282487B2 (ja) * | 2018-06-07 | 2023-05-29 | キヤノンメディカルシステムズ株式会社 | 医用画像診断装置 |
US10969935B2 (en) | 2018-06-08 | 2021-04-06 | Microsoft Technology Licensing, Llc | System for generation of novel artifacts with user-guided discovery and navigation of the creative space |
EP3803712A4 (fr) * | 2018-06-08 | 2022-04-20 | Nokia Technologies Oy | Appareil, procédé et programme informatique pour sélectionner un réseau neuronal |
CN108900848B (zh) * | 2018-06-12 | 2021-03-02 | 福建帝视信息科技有限公司 | 一种基于自适应可分离卷积的视频质量增强方法 |
CN109146777B (zh) * | 2018-06-15 | 2020-10-27 | 国网浙江省电力有限公司 | 利用预训练网络的感知相似性进行混合图像超分辨方法 |
US10692184B2 (en) | 2018-07-05 | 2020-06-23 | SVXR, Inc. | Super-resolution X-ray imaging method and apparatus |
KR102570562B1 (ko) * | 2018-07-16 | 2023-08-24 | 삼성전자주식회사 | 영상 처리 장치 및 그 동작방법 |
KR102022648B1 (ko) | 2018-08-10 | 2019-09-19 | 삼성전자주식회사 | 전자 장치, 이의 제어 방법 및 서버의 제어 방법 |
CN109190520A (zh) * | 2018-08-16 | 2019-01-11 | 广州视源电子科技股份有限公司 | 一种超分辨率重建人脸图像方法及装置 |
US10332035B1 (en) * | 2018-08-29 | 2019-06-25 | Capital One Services, Llc | Systems and methods for accelerating model training in machine learning |
CN112602088B (zh) * | 2018-09-06 | 2024-03-12 | Oppo广东移动通信有限公司 | 提高弱光图像的质量的方法、系统和计算机可读介质 |
US11062210B2 (en) | 2018-10-02 | 2021-07-13 | Nokia Technologies Oy | Method and apparatus for training a neural network used for denoising |
CN109361919A (zh) * | 2018-10-09 | 2019-02-19 | 四川大学 | 一种联合超分辨率和去压缩效应的图像编码性能提升方法 |
US11429867B2 (en) | 2018-10-11 | 2022-08-30 | International Business Machines Corporation | Down-sampling for convolutional neural networks |
WO2020080665A1 (fr) | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Procédés et appareils permettant d'effectuer un codage par intelligence artificielle et un décodage par intelligence artificielle sur une image |
KR102525578B1 (ko) * | 2018-10-19 | 2023-04-26 | 삼성전자주식회사 | 부호화 방법 및 그 장치, 복호화 방법 및 그 장치 |
WO2020080873A1 (fr) | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Procédé et appareil pour diffuser en continu des données |
KR20200044653A (ko) | 2018-10-19 | 2020-04-29 | 삼성전자주식회사 | 딥 뉴럴 네트워크를 이용한 영상의 ai 부호화 및 ai 복호화 방법, 및 장치 |
US11720997B2 (en) | 2018-10-19 | 2023-08-08 | Samsung Electronics Co.. Ltd. | Artificial intelligence (AI) encoding device and operating method thereof and AI decoding device and operating method thereof |
WO2020080751A1 (fr) * | 2018-10-19 | 2020-04-23 | 삼성전자 주식회사 | Procédé de codage et appareil associé, procédé de décodage et appareil associé |
WO2020080698A1 (fr) | 2018-10-19 | 2020-04-23 | 삼성전자 주식회사 | Procédé et dispositif d'évaluation de la qualité subjective d'une vidéo |
KR102525576B1 (ko) * | 2018-10-19 | 2023-04-26 | 삼성전자주식회사 | 영상의 ai 부호화 및 ai 복호화 방법, 및 장치 |
KR102525577B1 (ko) * | 2018-10-19 | 2023-04-26 | 삼성전자주식회사 | 데이터 스트리밍 방법 및 장치 |
WO2020080827A1 (fr) | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Appareil de codage d'ia et son procédé de fonctionnement, et appareil de décodage d'ia et son procédé de fonctionnement |
WO2020080765A1 (fr) | 2018-10-19 | 2020-04-23 | Samsung Electronics Co., Ltd. | Appareils et procédés permettant d'effectuer un codage par intelligence artificielle et un décodage par intelligence artificielle sur une image |
AU2018353930B2 (en) * | 2018-10-24 | 2020-10-08 | Advanced New Technologies Co., Ltd. | Fast computation of convolutional neural network |
CN109410141B (zh) * | 2018-10-26 | 2021-03-02 | 北京金山云网络技术有限公司 | 一种图像处理方法、装置、电子设备及存储介质 |
CN109448070B (zh) * | 2018-11-06 | 2020-10-09 | 明峰医疗系统股份有限公司 | 一种ct宽展视野的重建方法 |
JP7024687B2 (ja) * | 2018-11-07 | 2022-02-24 | 日本電信電話株式会社 | データ分析システム、学習装置、方法、及びプログラム |
CN112889069B (zh) * | 2018-11-08 | 2024-04-05 | Oppo广东移动通信有限公司 | 用于提高低照度图像质量的方法、系统和计算机可读介质 |
CN111178491A (zh) * | 2018-11-09 | 2020-05-19 | 佳能株式会社 | 神经网络模型的训练和应用方法、装置、系统及存储介质 |
KR102622950B1 (ko) * | 2018-11-12 | 2024-01-10 | 삼성전자주식회사 | 디스플레이장치, 그 제어방법 및 기록매체 |
US11409986B2 (en) * | 2018-11-15 | 2022-08-09 | Intel Corporation | Trainable vision scaler |
KR20200057849A (ko) * | 2018-11-15 | 2020-05-27 | 삼성전자주식회사 | 영상의 리타겟팅을 위한 영상 처리 장치 및 방법 |
KR20200063303A (ko) * | 2018-11-19 | 2020-06-05 | 삼성전자주식회사 | 영상 처리 장치 및 그 제어방법 |
CN113168684B (zh) * | 2018-11-26 | 2024-04-05 | Oppo广东移动通信有限公司 | 提升低亮度图像的质量的方法、系统和计算机可读介质 |
CN109495741B (zh) * | 2018-11-29 | 2023-03-31 | 四川大学 | 基于自适应下采样和深度学习的图像压缩方法 |
US11601644B2 (en) * | 2018-12-11 | 2023-03-07 | Google Llc | Image and video coding using machine learning prediction coding models |
KR102641423B1 (ko) * | 2018-12-11 | 2024-02-28 | 삼성전자주식회사 | 영상 처리 장치 및 그 동작방법 |
US10909659B2 (en) * | 2018-12-12 | 2021-02-02 | Apical Limited | Super-resolution image processing using a machine learning system |
CN109685750A (zh) * | 2018-12-14 | 2019-04-26 | 厦门美图之家科技有限公司 | 图像增强方法及计算设备 |
US10963757B2 (en) | 2018-12-14 | 2021-03-30 | Industrial Technology Research Institute | Neural network model fusion method and electronic device using the same |
CN109767386A (zh) * | 2018-12-22 | 2019-05-17 | 昆明理工大学 | 一种基于深度学习的快速图像超分辨率重建方法 |
RU2697928C1 (ru) | 2018-12-28 | 2019-08-21 | Самсунг Электроникс Ко., Лтд. | Способ сверхразрешения изображения, имитирующего повышение детализации на основе оптической системы, выполняемый на мобильном устройстве, обладающем ограниченными ресурсами, и мобильное устройство, его реализующее |
IN201911000737A (fr) * | 2019-01-07 | 2019-09-22 | Hcl Technologies Limited | |
US11080835B2 (en) * | 2019-01-09 | 2021-08-03 | Disney Enterprises, Inc. | Pixel error detection system |
US11521131B2 (en) * | 2019-01-24 | 2022-12-06 | Jumio Corporation | Systems and methods for deep-learning based super-resolution using multiple degradations on-demand learning |
CN109886990B (zh) * | 2019-01-29 | 2021-04-13 | 理光软件研究所(北京)有限公司 | 一种基于深度学习的图像分割系统 |
CN113711594A (zh) | 2019-02-15 | 2021-11-26 | 诺基亚技术有限公司 | 用于视频编码和解码的装置、方法和计算机程序 |
US11487739B2 (en) * | 2019-02-19 | 2022-11-01 | Nasdaq, Inc. | System and methods for data model detection and surveillance |
WO2020172019A1 (fr) * | 2019-02-20 | 2020-08-27 | Saudi Arabian Oil Company | Procédé de calcul rapide d'attributs sismiques à l'aide de l'intelligence artificielle |
KR20210135502A (ko) | 2019-03-08 | 2021-11-15 | 베이징 바이트댄스 네트워크 테크놀로지 컴퍼니, 리미티드 | 비디오 처리에서 변형 정보의 시그널링 |
CN113574897A (zh) | 2019-03-24 | 2021-10-29 | Oppo广东移动通信有限公司 | 滤波方法及装置、计算机存储介质 |
KR20200114436A (ko) * | 2019-03-28 | 2020-10-07 | 국방과학연구소 | 스케일러블 영상 부호화를 수행하는 장치 및 방법 |
US10909700B2 (en) * | 2019-04-02 | 2021-02-02 | Samsung Electronics Co., Ltd. | Display apparatus and image processing method thereof |
CN113692741B (zh) | 2019-04-18 | 2022-12-13 | 北京字节跳动网络技术有限公司 | 跨分量模式中的参数推导 |
BR112021019675A2 (pt) | 2019-04-23 | 2021-12-07 | Beijing Bytedance Network Tech Co Ltd | Método para processamento de mídia visual, aparelho codificador de vídeo, aparelho decodificador de vídeo, e, mídia legível por computador |
CN110147252A (zh) * | 2019-04-28 | 2019-08-20 | 深兰科技(上海)有限公司 | 一种卷积神经网络的并行计算方法及装置 |
US20220215511A1 (en) * | 2019-04-29 | 2022-07-07 | Deep Render Ltd | System and method for lossy image and video compression and/or transmission utilizing a metanetwork or neural networks |
WO2020227179A1 (fr) * | 2019-05-03 | 2020-11-12 | Amazon Technologies, Inc. | Amélioration vidéo à l'aide d'un réseau neuronal |
US11216917B2 (en) | 2019-05-03 | 2022-01-04 | Amazon Technologies, Inc. | Video enhancement using a neural network |
US11210769B2 (en) | 2019-05-03 | 2021-12-28 | Amazon Technologies, Inc. | Video enhancement using a recurrent image date of a neural network |
US20220222776A1 (en) * | 2019-05-03 | 2022-07-14 | Huawei Technologies Co., Ltd. | Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution |
US11017506B2 (en) | 2019-05-03 | 2021-05-25 | Amazon Technologies, Inc. | Video enhancement using a generator with filters of generative adversarial network |
WO2020225252A1 (fr) * | 2019-05-06 | 2020-11-12 | Sony Corporation | Dispositif électronique, procédé et programme d'ordinateur |
CN110121110B (zh) * | 2019-05-07 | 2021-05-25 | 北京奇艺世纪科技有限公司 | 视频质量评估方法、设备、视频处理设备及介质 |
KR102641796B1 (ko) | 2019-05-08 | 2024-03-04 | 베이징 바이트댄스 네트워크 테크놀로지 컴퍼니, 리미티드 | 교차-성분 코딩의 적용가능성에 대한 조건들 |
KR102236582B1 (ko) | 2019-05-14 | 2021-04-06 | 삼성전자주식회사 | 영상 처리 장치 및 그 동작방법 |
CN110163802B (zh) * | 2019-05-20 | 2020-09-01 | 电子科技大学 | 一种基于神经网络的sar图像超分辨方法 |
CN110099280B (zh) * | 2019-05-24 | 2020-05-08 | 浙江大学 | 一种无线自组织网络带宽受限下的视频业务质量增强方法 |
CN112085652A (zh) * | 2019-06-14 | 2020-12-15 | 深圳市中兴微电子技术有限公司 | 一种图像处理的方法、装置、计算机存储介质及终端 |
CN113994697A (zh) | 2019-06-22 | 2022-01-28 | 北京字节跳动网络技术有限公司 | 色度残差缩放的语法元素 |
KR20210004702A (ko) | 2019-07-05 | 2021-01-13 | 삼성전자주식회사 | Ai 프로세서 및 이의 신경망 연산 수행 방법 |
JP7460748B2 (ja) | 2019-07-07 | 2024-04-02 | 北京字節跳動網絡技術有限公司 | クロマ残差スケーリングのシグナリング |
CN110378976B (zh) * | 2019-07-18 | 2020-11-13 | 北京市商汤科技开发有限公司 | 图像处理方法及装置、电子设备和存储介质 |
CN110428378B (zh) | 2019-07-26 | 2022-02-08 | 北京小米移动软件有限公司 | 图像的处理方法、装置及存储介质 |
CN112308200B (zh) * | 2019-07-30 | 2024-04-26 | 华为技术有限公司 | 神经网络的搜索方法及装置 |
CN110650339A (zh) * | 2019-08-08 | 2020-01-03 | 合肥图鸭信息科技有限公司 | 一种视频压缩方法、装置及终端设备 |
US10839565B1 (en) * | 2019-08-19 | 2020-11-17 | Samsung Electronics Co., Ltd. | Decoding apparatus and operating method of the same, and artificial intelligence (AI) up-scaling apparatus and operating method of the same |
KR102248097B1 (ko) * | 2019-08-19 | 2021-05-06 | 네이버 주식회사 | 컨텐츠전송방법 및 이를 이용한 컨텐츠 생성 단말 |
US11551054B2 (en) | 2019-08-27 | 2023-01-10 | International Business Machines Corporation | System-aware selective quantization for performance optimized distributed deep learning |
US10972749B2 (en) * | 2019-08-29 | 2021-04-06 | Disney Enterprises, Inc. | Systems and methods for reconstructing frames |
US20220286746A1 (en) * | 2019-08-30 | 2022-09-08 | Sony Group Corporation | Reception device and reception method and transmission device and transmission method |
US11012718B2 (en) | 2019-08-30 | 2021-05-18 | Disney Enterprises, Inc. | Systems and methods for generating a latent space residual |
US11392799B2 (en) * | 2019-09-09 | 2022-07-19 | Apple Inc. | Method for improving temporal consistency of deep neural networks |
EP4028984A4 (fr) * | 2019-09-11 | 2023-01-11 | The State of Israel, Ministry of Agriculture & Rural Development, Agricultural Research Organization (ARO) (Volcani Center) | Procédés et systèmes de super-résolution pour imagerie infrarouge |
KR102166337B1 (ko) * | 2019-09-17 | 2020-10-15 | 삼성전자주식회사 | 영상의 ai 부호화 방법 및 장치, 영상의 ai 복호화 방법 및 장치 |
KR20190117416A (ko) * | 2019-09-26 | 2019-10-16 | 엘지전자 주식회사 | 동영상 프레임 해상도를 향상시키기 위한 방법 및 장치 |
US11445222B1 (en) * | 2019-09-30 | 2022-09-13 | Isize Limited | Preprocessing image data |
US10789354B1 (en) * | 2019-10-01 | 2020-09-29 | Capital One Services, Llc | Computer-based systems configured for detecting and sandboxing external resources and methods of use thereof |
US11341688B2 (en) | 2019-10-02 | 2022-05-24 | Nokia Technologies Oy | Guiding decoder-side optimization of neural network filter |
KR102624027B1 (ko) | 2019-10-17 | 2024-01-11 | 삼성전자주식회사 | 영상 처리 장치 및 방법 |
KR102436512B1 (ko) | 2019-10-29 | 2022-08-25 | 삼성전자주식회사 | 부호화 방법 및 그 장치, 복호화 방법 및 그 장치 |
DE102019217147A1 (de) * | 2019-11-06 | 2021-05-06 | Robert Bosch Gmbh | Verwendung von Kostenkarten und Konvergenzkarten zur Lokalisierung und Kartierung |
KR20210056179A (ko) * | 2019-11-08 | 2021-05-18 | 삼성전자주식회사 | Ai 부호화 장치 및 그 동작방법, 및 ai 복호화 장치 및 그 동작방법 |
CN110853040B (zh) * | 2019-11-12 | 2023-04-28 | 北京深境智能科技有限公司 | 一种基于超分辨率重建的图像协同分割方法 |
WO2021096159A1 (fr) | 2019-11-15 | 2021-05-20 | 한국과학기술원 | Système et procédé d'ingestion de vidéo en direct |
US11544815B2 (en) * | 2019-11-18 | 2023-01-03 | Advanced Micro Devices, Inc. | Gaming super resolution |
US11556784B2 (en) | 2019-11-22 | 2023-01-17 | Samsung Electronics Co., Ltd. | Multi-task fusion neural network architecture |
KR20210067699A (ko) * | 2019-11-29 | 2021-06-08 | 삼성전자주식회사 | 전자 장치 및 그 제어 방법 |
US20210192019A1 (en) * | 2019-12-18 | 2021-06-24 | Booz Allen Hamilton Inc. | System and method for digital steganography purification |
KR20210078218A (ko) * | 2019-12-18 | 2021-06-28 | 삼성전자주식회사 | 전자장치 및 그 제어방법 |
CN111083498B (zh) * | 2019-12-18 | 2021-12-21 | 杭州师范大学 | 用于视频编码帧间环路滤波的模型训练方法和使用方法 |
EP3846476B1 (fr) * | 2020-01-05 | 2023-09-20 | Isize Limited | Pré-traitement des données d'image |
WO2021139380A1 (fr) * | 2020-01-10 | 2021-07-15 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Procédé et dispositif de traitement d'image, et dispositif électronique |
US11206438B2 (en) | 2020-01-17 | 2021-12-21 | Amazon Technologies, Inc. | Video enhancement service |
KR102130077B1 (ko) * | 2020-02-19 | 2020-07-03 | 주식회사 지디에프랩 | 격자 생성 패턴 정보를 바탕으로 해상도를 개선하는 시스템 |
KR102130078B1 (ko) * | 2020-02-19 | 2020-07-03 | 주식회사 지디에프랩 | 해상도 향상도를 바탕으로 인공지능 파라미터를 변경하는 시스템 |
KR102130076B1 (ko) * | 2020-02-19 | 2020-07-03 | 주식회사 지디에프랩 | 특징 영역의 학습 중요도를 바탕으로 스트리밍 파일의 해상도를 개선하는 방법 |
KR102287942B1 (ko) | 2020-02-24 | 2021-08-09 | 삼성전자주식회사 | 전처리를 이용한 영상의 ai 부호화 및 ai 복호화 방법, 및 장치 |
WO2021206687A1 (fr) * | 2020-04-07 | 2021-10-14 | Purdue Research Foundation | Suréchantillonnage d'images |
CN113518227B (zh) * | 2020-04-09 | 2023-02-10 | 于江鸿 | 数据处理的方法和系统 |
US11288771B2 (en) * | 2020-04-29 | 2022-03-29 | Adobe Inc. | Texture hallucination for large-scale image super-resolution |
CN111696034B (zh) * | 2020-05-11 | 2023-10-27 | 青岛小鸟看看科技有限公司 | 图像处理方法、装置及电子设备 |
CN111683250B (zh) * | 2020-05-13 | 2021-03-16 | 武汉大学 | 一种基于深度学习的生成式遥感图像压缩方法 |
US11223841B2 (en) * | 2020-05-29 | 2022-01-11 | Samsung Electronics Co., Ltd. | Apparatus and method for performing artificial intelligence encoding and artificial intelligence decoding on image |
US11205077B1 (en) * | 2020-05-29 | 2021-12-21 | Arm Limited | Operating on a video frame to generate a feature map of a neural network |
TWI768364B (zh) * | 2020-06-01 | 2022-06-21 | 宏碁股份有限公司 | 處理可播放於一虛擬裝置的圖片的方法及電子裝置 |
CN111402143B (zh) * | 2020-06-03 | 2020-09-04 | 腾讯科技(深圳)有限公司 | 图像处理方法、装置、设备及计算机可读存储介质 |
CN111737909B (zh) * | 2020-06-10 | 2021-02-09 | 哈尔滨工业大学 | 基于时空图卷积网络的结构健康监测数据异常识别方法 |
WO2021251614A1 (fr) | 2020-06-12 | 2021-12-16 | Samsung Electronics Co., Ltd. | Appareil de traitement d'image et son procédé de fonctionnement |
US11436703B2 (en) * | 2020-06-12 | 2022-09-06 | Samsung Electronics Co., Ltd. | Method and apparatus for adaptive artificial intelligence downscaling for upscaling during video telephone call |
CN111899759B (zh) * | 2020-07-27 | 2021-09-03 | 北京嘀嘀无限科技发展有限公司 | 音频数据的预训练、模型训练方法、装置、设备及介质 |
CN112070657B (zh) * | 2020-08-14 | 2024-02-27 | 昀光微电子(上海)有限公司 | 图像处理方法、装置、系统、设备及计算机存储介质 |
US11908103B2 (en) * | 2020-08-14 | 2024-02-20 | Tencent America LLC | Multi-scale-factor image super resolution with micro-structured masks |
US20220067879A1 (en) | 2020-09-03 | 2022-03-03 | Nvidia Corporation | Image enhancement using one or more neural networks |
EP3975105A1 (fr) * | 2020-09-25 | 2022-03-30 | Aptiv Technologies Limited | Procédé et système d'interpolation et procédé et système de détermination d'une carte d'un environnement d'un véhicule |
US11792438B2 (en) * | 2020-10-02 | 2023-10-17 | Lemon Inc. | Using neural network filtering in video coding |
CA3195077A1 (fr) * | 2020-10-07 | 2022-04-14 | Dante DE NIGRIS | Systemes et procedes de segmentation d'images 3d |
US20230389817A1 (en) * | 2020-10-29 | 2023-12-07 | Hewlett-Packard Development Company, L.P. | Neural networks to determine respiration rates |
US11683358B2 (en) | 2020-11-04 | 2023-06-20 | Microsoft Technology Licensing, Llc | Dynamic user-device upscaling of media streams |
CN112465701B (zh) * | 2020-11-26 | 2023-08-29 | 上海健康医学院 | 显微图像的深度学习超分辨率重建方法、介质及电子设备 |
AU2020281143B1 (en) * | 2020-12-04 | 2021-03-25 | Commonwealth Scientific And Industrial Research Organisation | Creating super-resolution images |
DE102020215461A1 (de) * | 2020-12-08 | 2022-06-09 | Robert Bosch Gesellschaft mit beschränkter Haftung | Vorrichtung und Verfahren zum Trainieren eines Bildgenerators |
KR20220081648A (ko) * | 2020-12-09 | 2022-06-16 | 삼성전자주식회사 | Ai 부호화 장치 및 그 동작방법, 및 ai 복호화 장치 및 그 동작방법 |
DE102020215852B4 (de) * | 2020-12-14 | 2022-07-28 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung eingetragener Verein | Robuste Ankunftszeitschätzung unter Verwendung von faltenden neuronalen Netzerken (oder anderen Funktionsapproximationen) auf randomisierten Kanalmodellen |
CN112714321B (zh) * | 2020-12-18 | 2022-11-22 | 深圳大学 | 压缩视频处理方法、装置、设备及计算机可读存储介质 |
CN112541878A (zh) * | 2020-12-24 | 2021-03-23 | 北京百度网讯科技有限公司 | 建立图像增强模型与图像增强的方法、装置 |
TWI766522B (zh) * | 2020-12-31 | 2022-06-01 | 鴻海精密工業股份有限公司 | 資料處理方法、裝置、電子設備及存儲介質 |
FR3118747A1 (fr) * | 2021-01-11 | 2022-07-15 | Psa Automobiles Sa | Procédé et dispositif de détermination d’information représentative d’adhérence entre un véhicule et un revêtement d’une route |
US11451744B2 (en) | 2021-01-21 | 2022-09-20 | Dell Products, Lp | Lighting, color vector, and virtual background correction during a video conference session |
US11310464B1 (en) | 2021-01-24 | 2022-04-19 | Dell Products, Lp | System and method for seviceability during execution of a video conferencing application using intelligent contextual session management |
WO2022182353A1 (fr) * | 2021-02-26 | 2022-09-01 | Hewlett-Packard Development Company, L.P. | Amélioration d'image de document capturé |
US11271984B1 (en) * | 2021-03-29 | 2022-03-08 | International Business Machines Corporation | Reduced bandwidth consumption via generative adversarial networks |
US11924415B2 (en) | 2021-05-11 | 2024-03-05 | Tencent America LLC | Method and apparatus for boundary handling in video coding |
CN113507607B (zh) * | 2021-06-11 | 2023-05-26 | 电子科技大学 | 一种无需运动补偿的压缩视频多帧质量增强方法 |
US11997326B2 (en) | 2021-11-30 | 2024-05-28 | Samsung Electronics Co., Ltd. | Method of streaming image content between server and electronic device, server for streaming image content, and electronic device for streaming image content |
CN114235970B (zh) * | 2021-12-20 | 2024-04-23 | 西安科技大学 | 一种自适应超声重叠回波分离方法 |
WO2023199172A1 (fr) * | 2022-04-11 | 2023-10-19 | Nokia Technologies Oy | Appareil et procédé d'optimisation de surajustement de filtres de réseau neuronal |
CN114845138A (zh) * | 2022-04-26 | 2022-08-02 | 三星电子(中国)研发中心 | 自适应流媒体的超分辨率重建方法和装置及服务器 |
CN115879516B (zh) * | 2023-03-02 | 2023-05-16 | 南昌大学 | 一种数据取证方法 |
CN116527833B (zh) * | 2023-07-03 | 2023-09-05 | 清华大学 | 一种基于超分模型的高清视频生成方法及系统 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008133951A2 (fr) * | 2007-04-24 | 2008-11-06 | Massachusetts Institute Of Technology | Procédé et appareil de traitement d'image |
Family Cites Families (86)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3037010A (en) | 1957-11-27 | 1962-05-29 | Du Pont | Polymeric perfluoro-2-butyne |
JPS6421385A (en) | 1987-07-17 | 1989-01-24 | Seiko Epson Corp | Preparation of dial for clock |
FR2646575A1 (fr) * | 1989-04-26 | 1990-11-02 | Labo Electronique Physique | Procede et structure pour la compression de donnees |
DE4326487C2 (de) | 1992-09-16 | 1995-02-09 | Konrad Michael Dipl Ing Weigl | Adaptives Filter |
US5376962A (en) | 1993-03-31 | 1994-12-27 | Panasonic Technologies, Inc. | Neural network video image processor |
KR0139154B1 (ko) | 1994-07-08 | 1998-06-15 | 김광호 | 신경망을 이용한 부호화방법 및 그 장치 |
WO1997039417A2 (fr) | 1996-03-29 | 1997-10-23 | Sarnoff Corporation | Methode et dispositif pour entrainer un reseau de neurones a apprendre et a utiliser la metrique de fidelite comme mecanisme de controle |
US6075884A (en) | 1996-03-29 | 2000-06-13 | Sarnoff Corporation | Method and apparatus for training a neural network to learn and use fidelity metric as a control mechanism |
JPH1021385A (ja) | 1996-07-03 | 1998-01-23 | N T T Data Tsushin Kk | 画像処理方法及び装置 |
US5831678A (en) | 1996-08-09 | 1998-11-03 | U.S. Robotics Access Corp. | Video encoder/decoder system |
AU2352100A (en) | 1998-12-03 | 2000-06-19 | Qbeo, Inc. | Digital image improvement through genetic image evolution |
US6470097B1 (en) | 1999-01-22 | 2002-10-22 | Siemens Corporation Research, Inc. | Total variational blind image restoration from image sequences |
JP4234420B2 (ja) | 2000-07-06 | 2009-03-04 | ザ トラスティーズ オブ コロンビア ユニヴァーシティ イン ザ シティ オブ ニューヨーク | データ解像度を増す方法および装置 |
US7133568B2 (en) | 2000-08-04 | 2006-11-07 | Nikitin Alexei V | Method and apparatus for analysis of variables |
US6735336B2 (en) | 2001-05-16 | 2004-05-11 | Applied Neural Computing Ltd. | Apparatus for and method of pattern recognition and image analysis |
KR20030009575A (ko) | 2001-06-26 | 2003-02-05 | 박광훈 | 신경망 분류기를 이용한 동영상 전송률 제어 장치 및 그방법 |
US7298412B2 (en) | 2001-09-18 | 2007-11-20 | Ricoh Company, Limited | Image pickup device, automatic focusing method, automatic exposure method, electronic flash control method and computer program |
US7599434B2 (en) | 2001-09-26 | 2009-10-06 | Reynolds Jodie L | System and method for compressing portions of a media signal using different codecs |
US6874690B2 (en) | 2002-01-11 | 2005-04-05 | Metrologic Instruments, Inc. | Modular omnidirectional bar code symbol scanning system with at least one service port for removable installation of scan module insert |
GB0209780D0 (en) | 2002-04-29 | 2002-06-05 | Neural Technologies Ltd | Method of encoding data for decoding data from and constraining a neural network |
US7343278B2 (en) | 2002-10-22 | 2008-03-11 | Artoolworks, Inc. | Tracking a surface in a 3-dimensional scene using natural visual features of the surface |
US7135170B2 (en) | 2002-10-23 | 2006-11-14 | Zymogenetics, Inc. | Methods for treating viral infection using IL-28 and IL-29 |
KR100529311B1 (ko) | 2003-01-21 | 2005-11-17 | 삼성전자주식회사 | 신경 회로망을 이용하여 가변 길이 부호화 비트 스트림의길이를 선택하는 장치 및 방법 |
US7218796B2 (en) * | 2003-04-30 | 2007-05-15 | Microsoft Corporation | Patch-based video super-resolution |
KR100594056B1 (ko) | 2003-09-01 | 2006-07-03 | 삼성전자주식회사 | 효율적인 비트율 제어를 위한 h.263/mpeg 비디오인코더 및 그 제어 방법 |
WO2005072337A2 (fr) * | 2004-01-23 | 2005-08-11 | Sarnoff Corporation | Procede et dispositif destines a la reconstruction de donnes de video numerique |
JP2005352900A (ja) | 2004-06-11 | 2005-12-22 | Canon Inc | 情報処理装置、情報処理方法、パターン認識装置、及びパターン認識方法 |
US7876833B2 (en) * | 2005-04-11 | 2011-01-25 | Sharp Laboratories Of America, Inc. | Method and apparatus for adaptive up-scaling for spatially scalable coding |
US7623731B2 (en) | 2005-06-20 | 2009-11-24 | Honda Motor Co., Ltd. | Direct method for modeling non-rigid motion with thin plate spline transformation |
FR2889778A1 (fr) | 2005-08-12 | 2007-02-16 | Thomson Licensing Sas | Procede de codage et de decodage d'images video avec echelonnabilite spatiale |
CN101053249B (zh) | 2005-09-09 | 2011-02-16 | 松下电器产业株式会社 | 图像处理方法、图像存储方法、图像处理装置及文件格式 |
WO2008106615A1 (fr) | 2007-02-28 | 2008-09-04 | Numenta, Inc. | Algorithmes d'apprentissage spatiotemporel dans des réseaux temporels hiérarchiques |
US7747107B2 (en) | 2007-03-06 | 2010-06-29 | Mitsubishi Electric Research Laboratories, Inc. | Method for retargeting images |
US8331615B2 (en) | 2007-08-01 | 2012-12-11 | The Board Of Trustees Of The University Of Illinois | Match, expand, and filter technique for multi-view stereopsis |
CA2638465A1 (fr) * | 2007-08-01 | 2009-02-01 | Jean-Yves Chouinard | Filtres d'apprentissage permettant d'ameliorer la qualite des images fixes et des images video a codage de bloc |
US8223837B2 (en) | 2007-09-07 | 2012-07-17 | Microsoft Corporation | Learning-based image compression |
US20090110285A1 (en) | 2007-10-26 | 2009-04-30 | Technion Research And Development Foundation Ltd | Apparatus and method for improving image resolution using fuzzy motion estimation |
US8306121B2 (en) | 2008-03-17 | 2012-11-06 | Ati Technologies Ulc | Method and apparatus for super-resolution of images |
CN101621683A (zh) | 2008-07-01 | 2010-01-06 | 邹采荣 | 一种基于avs的快速立体视频编码方法 |
KR100963424B1 (ko) | 2008-07-23 | 2010-06-15 | 한국전자통신연구원 | 스케일러블 영상 복호화기 및 그 제어 방법 |
US8731255B2 (en) | 2008-11-05 | 2014-05-20 | University Of Louisville Research Foundation, Inc. | Computer aided diagnostic system incorporating lung segmentation and registration |
CN102763123B (zh) | 2009-12-02 | 2015-03-25 | 高通股份有限公司 | 通过使查询图像和模型图像中的检测到的关键点成群集而进行特征匹配 |
CN102823242B (zh) | 2010-01-22 | 2016-08-10 | 汤姆森特许公司 | 基于取样超分辨率视频编码和解码的方法和装置 |
CN102726044B (zh) * | 2010-01-22 | 2016-08-10 | 汤姆逊许可证公司 | 使用基于示例的超分辨率的用于视频压缩的数据剪切 |
CN102148996A (zh) | 2010-02-04 | 2011-08-10 | 成都市世嘉电子实业有限公司 | 帧内宏块预测模式判定方法 |
US8521664B1 (en) | 2010-05-14 | 2013-08-27 | Google Inc. | Predictive analytical model matching |
US8428390B2 (en) | 2010-06-14 | 2013-04-23 | Microsoft Corporation | Generating sharp images, panoramas, and videos from motion-blurred videos |
EP2410746A1 (fr) | 2010-07-20 | 2012-01-25 | Siemens Aktiengesellschaft | Codage vidéo utilisant des trames de référence à haute résolution |
WO2012012582A1 (fr) | 2010-07-21 | 2012-01-26 | Dolby Laboratories Licensing Corporation | Traitement de référence à l'aide de modèles de mouvement avancés pour l'encodage vidéo |
US8467599B2 (en) | 2010-09-02 | 2013-06-18 | Edge 3 Technologies, Inc. | Method and apparatus for confusion learning |
EP2557789B1 (fr) * | 2011-08-09 | 2017-09-27 | Dolby Laboratories Licensing Corporation | Échantillonnage d'image guidé dans un codage vidéo |
US8718407B2 (en) * | 2011-11-18 | 2014-05-06 | Stmicroelectronics (Canada), Inc. | High-quality single-frame superresolution training and reconstruction engine |
EP2810243A4 (fr) | 2012-01-25 | 2015-12-02 | Intel Corp | Redimensionnement d'image en fonction du contenu au moyen de super pixels |
US8620073B2 (en) | 2012-02-24 | 2013-12-31 | Mitsubishi Electric Research Laboratories, Inc. | Upscaling natural images |
CN103369349B (zh) | 2012-03-28 | 2016-04-27 | 中国移动通信集团公司 | 一种数字视频质量控制方法及其装置 |
KR102008078B1 (ko) | 2012-09-28 | 2019-08-06 | 브이아이디 스케일, 인크. | 다층 비디오 코딩을 위한 적응적 업샘플링 |
US9904889B2 (en) | 2012-12-05 | 2018-02-27 | Applied Brain Research Inc. | Methods and systems for artificial cognition |
US20140177706A1 (en) * | 2012-12-21 | 2014-06-26 | Samsung Electronics Co., Ltd | Method and system for providing super-resolution of quantized images and video |
US9924200B2 (en) * | 2013-01-24 | 2018-03-20 | Microsoft Technology Licensing, Llc | Adaptive noise reduction engine for streaming video |
KR102080859B1 (ko) * | 2013-04-08 | 2020-02-24 | 삼성전자주식회사 | 이미지 프로세서 및 이미지 프로세서의 이미지 처리 방법 |
EP2989607B1 (fr) | 2013-04-25 | 2019-01-09 | Thomson Licensing | Procédé et dispositif pour effectuer une super-résolution sur une image d'entrée |
EP2806374B1 (fr) | 2013-05-24 | 2022-07-06 | Tata Consultancy Services Limited | Procédé et système de sélection automatique d'un ou de plusieurs algorithmes de traitement d'image |
CA2915359C (fr) | 2013-06-14 | 2018-09-04 | Arris Technology, Inc. | Re-echantillonnage de filtres pour codage video evolutif |
KR102103984B1 (ko) | 2013-07-15 | 2020-04-23 | 삼성전자주식회사 | 깊이 영상 처리 방법 및 장치 |
US9195909B2 (en) | 2013-09-23 | 2015-11-24 | Adobe Systems Incorporated | Using machine learning to define user controls for photo adjustments |
US9668699B2 (en) | 2013-10-17 | 2017-06-06 | Siemens Healthcare Gmbh | Method and system for anatomical object detection using marginal space deep neural networks |
US9342870B2 (en) | 2013-10-22 | 2016-05-17 | Adobe Systems Incorporated | Tree-based linear regression for denoising |
US9208539B2 (en) | 2013-11-30 | 2015-12-08 | Sharp Laboratories Of America, Inc. | Image enhancement using semantic components |
JP6335504B2 (ja) | 2013-12-20 | 2018-05-30 | キヤノン株式会社 | 画像処理装置、画像処理方法及びプログラム |
US10846611B2 (en) | 2014-06-16 | 2020-11-24 | Nokia Technologies Oy | Data processing |
WO2015192316A1 (fr) * | 2014-06-17 | 2015-12-23 | Beijing Kuangshi Technology Co., Ltd. | Hallucination de visage obtenue à l'aide de réseaux neuronaux convolutionnels |
US9996768B2 (en) * | 2014-11-19 | 2018-06-12 | Adobe Systems Incorporated | Neural network patch aggregation and statistics |
EP3259920A1 (fr) | 2015-02-19 | 2017-12-27 | Magic Pony Technology Limited | Traitement visuel à l'aide d'une interpolation temporelle et spatiale |
WO2016156864A1 (fr) | 2015-03-31 | 2016-10-06 | Magic Pony Technology Limited | Apprentissage de processus vidéo bout-à-bout |
GB201603144D0 (en) | 2016-02-23 | 2016-04-06 | Magic Pony Technology Ltd | Training end-to-end video processes |
GB201604672D0 (en) | 2016-03-18 | 2016-05-04 | Magic Pony Technology Ltd | Generative methods of super resolution |
CN105120130B (zh) | 2015-09-17 | 2018-06-29 | 京东方科技集团股份有限公司 | 一种图像升频系统、其训练方法及图像升频方法 |
EP3166070B1 (fr) | 2015-11-09 | 2021-01-06 | InterDigital CE Patent Holdings | Procédé et appareil pour l'interpolation d'images bruitées |
US10648924B2 (en) | 2016-01-04 | 2020-05-12 | Kla-Tencor Corp. | Generating high resolution images from low resolution images for semiconductor applications |
CN105931179B (zh) | 2016-04-08 | 2018-10-26 | 武汉大学 | 一种联合稀疏表示与深度学习的图像超分辨率方法及系统 |
EP3298579B1 (fr) | 2016-04-12 | 2021-07-21 | Magic Pony Technology Limited | Traitement de données visuelles à l'aide des réseaux d'énergie |
GB201607994D0 (en) | 2016-05-06 | 2016-06-22 | Magic Pony Technology Ltd | Encoder pre-analyser |
WO2018053340A1 (fr) | 2016-09-15 | 2018-03-22 | Twitter, Inc. | Super résolution à l'aide d'un réseau contradictoire génératif |
KR102631381B1 (ko) * | 2016-11-07 | 2024-01-31 | 삼성전자주식회사 | 컨볼루션 신경망 처리 방법 및 장치 |
US10832168B2 (en) | 2017-01-10 | 2020-11-10 | Crowdstrike, Inc. | Computational modeling and classification of data streams |
US10572979B2 (en) | 2017-04-06 | 2020-02-25 | Pixar | Denoising Monte Carlo renderings using machine learning with importance sampling |
-
2016
- 2016-02-19 EP EP16706424.5A patent/EP3259920A1/fr not_active Withdrawn
- 2016-02-19 WO PCT/GB2016/050424 patent/WO2016132146A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050429 patent/WO2016132151A1/fr active Application Filing
- 2016-02-19 EP EP16706416.1A patent/EP3259916B1/fr active Active
- 2016-02-19 EP EP16706417.9A patent/EP3259913B1/fr active Active
- 2016-02-19 DE DE202016009102.7U patent/DE202016009102U1/de active Active
- 2016-02-19 GB GB1617475.7A patent/GB2539845B/en not_active Expired - Fee Related
- 2016-02-19 EP EP19152799.3A patent/EP3493149A1/fr not_active Withdrawn
- 2016-02-19 EP EP16706423.7A patent/EP3259912B1/fr active Active
- 2016-02-19 EP EP16706421.1A patent/EP3259919A1/fr not_active Withdrawn
- 2016-02-19 EP EP16706422.9A patent/EP3259914A1/fr not_active Withdrawn
- 2016-02-19 WO PCT/GB2016/050427 patent/WO2016132149A1/fr active Application Filing
- 2016-02-19 EP EP16706419.5A patent/EP3259918B1/fr active Active
- 2016-02-19 DE DE202016009091.8U patent/DE202016009091U1/de active Active
- 2016-02-19 EP EP16706415.3A patent/EP3259915A1/fr not_active Withdrawn
- 2016-02-19 GB GB1617478.1A patent/GB2539846B/en not_active Expired - Fee Related
- 2016-02-19 DE DE202016009089.6U patent/DE202016009089U1/de active Active
- 2016-02-19 GB GB1617481.5A patent/GB2543958B/en not_active Expired - Fee Related
- 2016-02-19 GB GB1617471.6A patent/GB2543429B/en not_active Expired - Fee Related
- 2016-02-19 WO PCT/GB2016/050426 patent/WO2016132148A1/fr active Application Filing
- 2016-02-19 DE DE202016009107.8U patent/DE202016009107U1/de active Active
- 2016-02-19 WO PCT/GB2016/050425 patent/WO2016132147A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050423 patent/WO2016132145A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050432 patent/WO2016132154A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050430 patent/WO2016132152A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050428 patent/WO2016132150A1/fr active Application Filing
- 2016-02-19 WO PCT/GB2016/050431 patent/WO2016132153A1/fr active Application Filing
- 2016-02-19 ES ES16706418T patent/ES2873845T3/es active Active
- 2016-02-19 EP EP16706420.3A patent/EP3259911B1/fr active Active
- 2016-02-19 DE DE202016009100.0U patent/DE202016009100U1/de active Active
- 2016-02-19 GB GB1617482.3A patent/GB2540889B/en not_active Expired - Fee Related
- 2016-02-19 DE DE202016009101.9U patent/DE202016009101U1/de active Active
- 2016-02-19 EP EP16706418.7A patent/EP3259910B1/fr active Active
- 2016-02-19 ES ES16706420T patent/ES2872724T3/es active Active
-
2017
- 2017-08-17 US US15/679,977 patent/US10523955B2/en not_active Expired - Fee Related
- 2017-08-17 US US15/679,984 patent/US11528492B2/en active Active
- 2017-08-17 US US15/679,965 patent/US10887613B2/en active Active
- 2017-08-17 US US15/679,660 patent/US10547858B2/en not_active Expired - Fee Related
- 2017-08-18 US US15/680,708 patent/US10516890B2/en not_active Expired - Fee Related
- 2017-08-18 US US15/680,761 patent/US10623756B2/en not_active Expired - Fee Related
- 2017-08-18 US US15/680,716 patent/US10499069B2/en not_active Expired - Fee Related
- 2017-08-18 US US15/680,862 patent/US10904541B2/en active Active
- 2017-08-18 US US15/680,753 patent/US10582205B2/en not_active Expired - Fee Related
- 2017-08-18 US US15/681,092 patent/US10630996B2/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008133951A2 (fr) * | 2007-04-24 | 2008-11-06 | Massachusetts Institute Of Technology | Procédé et appareil de traitement d'image |
Non-Patent Citations (1)
Title |
---|
DONG CHAO ET AL: "Learning a Deep Convolutional Network for Image Super-Resolution", 6 September 2014, CORRECT SYSTEM DESIGN; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER INTERNATIONAL PUBLISHING, CHAM, PAGE(S) 184 - 199, ISBN: 978-3-642-36361-0, ISSN: 0302-9743, XP047296566 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018125580A1 (fr) * | 2016-12-30 | 2018-07-05 | Konica Minolta Laboratory U.S.A., Inc. | Segmentation de glande à réseaux de déconvolution multi-niveaux supervisés en profondeur |
CN110378854A (zh) * | 2019-07-17 | 2019-10-25 | 上海商汤智能科技有限公司 | 机器人图像增强方法及装置 |
CN110378854B (zh) * | 2019-07-17 | 2021-10-26 | 上海商汤智能科技有限公司 | 机器人图像增强方法及装置 |
Also Published As
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11234006B2 (en) | Training end-to-end video processes | |
US10516890B2 (en) | Accelerating machine optimisation processes | |
GB2548749A (en) | Online training of hierarchical algorithms |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16706419 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2016706419 Country of ref document: EP |